search

declare-lab / MELD

MELD: A Multimodal Multi-Party Dataset for Emotion Recognition in Conversation
GNU General Public License v3.0
788 stars 200 forks source link

Is there any face region information in videos? #48

Open ByeongjunCho opened 1 year ago

ByeongjunCho commented 1 year ago

Hi, Thanks to share good datasets

I want to cut face region who speak in video frame, but many video frame has 2 more person.

Is this any face region information in videos? If any information(xy info, etc...) is exist, please share.

Thank you

rajendrac3 commented 4 weeks ago

Check this out https://github.com/facebookresearch/VisualVoice/tree/main